Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

xda-developers.com

Post reply on HN
Print view View original

151–159 of 159 posts

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#151

Post by trollbridge »

jchw wrote: post #88
medler wrote: post #19

Earlier quoted context omitted.

Qwen is very much censored. Just try asking it about Tiananmen or how to build a bomb. But it is nice that you can experiment with it locally without having to worry about your account getting nuked

You are misunderstanding what they said, they are saying you can use uncensored variants of models like Qwen when running locally. There are quite a lot of people working to "uncensor" open weights releases. It seems to work although it would be nice if some third party was benchmarking the uncensored variants regularly to give us an idea of how well retained their skills are.

Abliteratuon sloghtly reduces the strength of the model - in my opinion it’s around the same jump as going from 5 bit to 4 bit.

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#152

Post by taneq »

rustcleaner wrote: post #128
ninahaberl wrote: post #24

Earlier quoted context omitted.

I’d expect these shenanigans to get much worse over time for the average Joe. Imagine a world where any random person can run a super-capable model on their own hardware with no limitations and no one to pull the plug. Information has always been power and those who already have power won't just allow everyone else having the same tools as them

>Imagine a world where any random person can run a super-capable model on their own hardware with no limitations and no one to pull the plug. That would be my heaven. I wish that for you and Joe down the street, as much as I wish it for myself! I would fight and even die to defend your right to free compute. Will you do the same for me, brother?

Imagine an unholy fusion of The Anarchist’s Cookbook and A Young Lady’s Illustrated Primer, distributed to every malcontent with a smartphone.

At some point some kid is going to build a bioweapon for their school project.

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#153

Post by edg5000 »

badsectoracula wrote: post #140
willy_k wrote: post #69

Earlier quoted context omitted.

Because deleting model weights after training is likely to cause knock-on effects in model knowledge and/or behavior. Targetting it might mitigate this but it’s a) not guaranteed that only censor-ey parameters get removed, and b) likely that removing those parameters still has effects on the effectiveness of related parameters.

Considering these are essentially document completion engines[0], can't you just start the task with the version that doesn't refuse and then continue with the version that would refuse but now has to keep going after it accepted the task? :-P [0] in the sense that the "discussion" is basically a turn based game between you and the LLM filling a chat transcript document

The article proves your point. It's eventually proceeded once there was the right history. If he already had the exploit and wanted the model to write an implementation, faking the history could have tripped the model over the edge. So the guardrails aren't unsurmountable.

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#155

Post by mrkstu »

andai wrote: post #56
VulgarExigency wrote: post #5

> The first attempt at recovering the key was wrong in a very specific way; it produced a working key and the signature check passed, but a hash the binary computes as an integrity check didn't match. In my experience, most models would have called it done and left it at that, but Qwen 3.8 27B didn't do that. Instead, it highlighted the mismatch, went back to the drawing board, and kept going until the value matched…

Yeah, about a year ago the labs figured out that effective intelligence is a function of persistence as much as anything else. So the models started getting scary persistent late last year, and the trend has continued. There was another jump a few months ago.

Grit beats IQ yet again…

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#156

Post by jamaicahest »

mrkstu wrote: post #155
andai wrote: post #56

Earlier quoted context omitted.

Yeah, about a year ago the labs figured out that effective intelligence is a function of persistence as much as anything else. So the models started getting scary persistent late last year, and the trend has continued. There was another jump a few months ago.

Grit beats IQ yet again…

As long as retry is cheap enough..

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#158

Post by adamgoodapp »

TofuLover wrote: post #31
exceptione wrote: post #8

Local models would be even better if they did not ship with all the refusal shenanigans built-in. You can safely bet organized crime has access to the best models without these hoops, which makes the case that the average user (=non-criminal) should have access too. As I understood from an ex-Anthropic employee, some orgs got access to Mythos based on their high enough spending level, not on other grounds. Either we…

Completely coincidentally, we're just about to launch a service that does exactly this (API access to uncensored open models)! We have a waitlist at the moment but will be live very soon! https://violentdelights.ai

Would love to get a sub. Ive currently got three separate subscriptions to the models above and would be great to combine them. Coincidentally, I'm Read teaming and checking security issues for a company with the same name as you.

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#159

Post by ethbr1 »

jamaicahest wrote: post #156
mrkstu wrote: post #155

Earlier quoted context omitted.

Grit beats IQ yet again…

As long as retry is cheap enough..

And if the goal is non-interactive solution finding.

I used to do business automation work in day job, and there are surprising utility-to-humans differences between "manual" -> "helps interactively" -> "99% automated" -> "100% automated".

In the latter 2 categories, you almost don't care about runtime for most use cases, because meatbags require 8 hours of sleep / day.

As long as you have sufficient hardware+electricity to throw at the problem, that's a lot of time to inefficiently finish something. (Also: a lot of time for a model to get up to god-knows-what in a poorly sandboxed consumer environment... but that's a problem for future society)

Post reply on HN